EP 4033412 A2 20220727 - METHOD AND APPARATUS WITH NEURAL NETWORK TRAINING
Title (en)
METHOD AND APPARATUS WITH NEURAL NETWORK TRAINING
Title (de)
VERFAHREN UND GERÄT MIT NEURONALEM NETZWERKTRAINING
Title (fr)
PROCÉDÉ ET APPAREIL AVEC FORMATION DE RÉSEAU NEURONAL
Publication
Application
Priority
- KR 20210061877 A 20210513
- KR 20210009670 A 20210122
Abstract (en)
A processor-implemented method with neural network training includes: determining first backbone feature data corresponding to each input data by applying, to a first neural network model, two or more sets of the input data of the same scene, respectively; determining second backbone feature data corresponding to each input data by applying, to a second neural network model, the two or more sets of the input data, respectively; determining projection-based first embedded data and dropout-based first view data from the first backbone feature data; and determining projection-based second embedded data and dropout-based second view data from the second backbone feature data; and training either one or both of the first neural network model and the second neural network model based on a loss determined based on a combination of any two or more of the first embedded data, the first view data, the second embedded data, the second view data, and an embedded data clustering result.
IPC 8 full level
G01S 17/931 (2020.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01)
CPC (source: CN EP US)
G06F 18/2321 (2023.01 - CN); G06N 3/045 (2023.01 - CN EP US); G06N 3/08 (2013.01 - CN); G06N 3/082 (2013.01 - EP); G06N 3/084 (2013.01 - EP); G06V 10/762 (2022.01 - US); G06V 20/58 (2022.01 - US); G01S 17/931 (2020.01 - EP); G06N 3/044 (2023.01 - EP); G06N 3/048 (2023.01 - EP); G06N 3/063 (2013.01 - EP)
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
DOCDB simple family (publication)
EP 4033412 A2 20220727; EP 4033412 A3 20220914; CN 114819050 A 20220729; JP 2022113135 A 20220803; US 2022237890 A1 20220728
DOCDB simple family (application)
EP 22151396 A 20220113; CN 202210061402 A 20220119; JP 2022005573 A 20220118; US 202117550184 A 20211214